© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36392
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ობას
    0.38
     താമസ
    0.35
     запол
    0.34
    差点
    0.34
    感動
    0.33
    海岸
    0.33
     LOCATION
    0.33
    舖
    0.33
    ᖏ
    0.32
     jeden
    0.32
    POSITIVE LOGITS
     Ballot
    0.35
     drought
    0.35
     Drought
    0.34
     promoter
    0.32
    粈
    0.32
     case
    0.32
     cường
    0.32
     newItem
    0.32
     قلب
    0.32
    析
    0.32
    Activations Density 0.001%

    No Known Activations